There is an even more interactive version of this report built with ShinyR and found here.
We are looking at a simple earthquake dataset that contains entries from 1900 to early 2017 for events with 6 or more magnitudes. Exact query to fetch this data can be found here from USGS. Zoom in/out and click on events.
Next, we chart bucket counts for special magnitude ranges over the same time period.
##
## Welch Two Sample t-test
##
## data: filter(eq, period == "1900 - 1940" & magBins == "(6,7]")$mag and filter(eq, period == "1940 - 1980" & magBins == "(6,7]")$mag
## t = 27.191, df = 1663.2, p-value < 2.2e-16
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## 0.2390888 0.2762637
## sample estimates:
## mean of x mean of y
## 6.566196 6.308520##
## Welch Two Sample t-test
##
## data: filter(eq, period == "1940 - 1980" & magBins == "(6,7]")$mag and filter(eq, period == "1980 - 2017" & magBins == "(6,7]")$mag
## t = 0.59878, df = 8662.1, p-value = 0.5493
## alternative hypothesis: true difference in means is not equal to 0
## 95 percent confidence interval:
## -0.008390252 0.015770500
## sample estimates:
## mean of x mean of y
## 6.308520 6.304829These t-tests back the visualization above and give statistical evidence to suggest earthquake activities in the (6,7] magnitude range have been going up recently (1980 - 2017) compared to pre 1940; however same isn’t true when comparing with (1940 - 1980) data.
There is an even more interactive version of this report built with ShinyR and found here.